view release on metacpan or  search on metacpan

lib/AI/Embedding.pm  view on Meta::CPAN

 }

 # Return Embedding as a CSV string
 sub embedding {
     my ($self, $text, $verbose) = @_;

     my $response = $self->_get_embedding($text);
     if ($response->{'success'}) {
         my $embedding = decode_json($response->{'content'});
         return join (',', @{$embedding->{'data'}[0]->{'embedding'}});
     }
     $self->{'error'} = 'HTTP Error - ' . $response->{'reason'};
     return $response if defined $verbose;
     return undef;
 }

 # Return Embedding as an array
 sub raw_embedding {
     my ($self, $text, $verbose) = @_;

     my $response = $self->_get_embedding($text);
     if ($response->{'success'}) {
         my $embedding = decode_json($response->{'content'});
         return @{$embedding->{'data'}[0]->{'embedding'}};
     }
     $self->{'error'} = 'HTTP Error - ' . $response->{'reason'};
     return $response if defined $verbose;
     return undef;
 }

 # Return Test Embedding
 sub test_embedding {
     my ($self, $text, $dimension) = @_;
     $self->{'error'} = '';

     $dimension = 1536 unless defined $dimension;

     if ($text) {
         srand scalar split /\s+/, $text;
     }

     my @vector;
     for (1...$dimension) {
         push @vector, rand(2) - 1;
     }
     return join ',', @vector;
 }

# Convert a CSV Embedding into a hashref
sub _make_vector {
    my ($self, $embed_string) = @_;

    if (!defined $embed_string) {
        $self->{'error'} = 'Nothing to compare!';
        return;
    }

    my %vector;
    my @embed = split /,/, $embed_string;
    for (my $i = 0; $i < @embed; $i++) {
       $vector{'feature' . $i} = $embed[$i];
   }
   return \%vector;
}

# Return a comparator to compare to a set vector
sub comparator {
    my($self, $embed) = @_;
    $self->{'error'} = '';

    my $vector1 = $self->_make_vector($embed);
    return sub {
        my($embed2) = @_;
        my $vector2 = $self->_make_vector($embed2);
        return $self->_compare_vector($vector1, $vector2);
    };
}

# Compare 2 Embeddings
sub compare {
    my ($self, $embed1, $embed2) = @_;

    my $vector1 = $self->_make_vector($embed1);
    my $vector2;
    if (defined $embed2) {
        $vector2 = $self->_make_vector($embed2);
    } else {
        $vector2 = $self->{'comparator'};
    }

    if (!defined $vector2) {
        $self->{'error'} = 'Nothing to compare!';
        return;
    }

    if (scalar keys %$vector1 != scalar keys %$vector2) {
        $self->{'error'} = 'Embeds are unequal length';
        return;
    }

    return $self->_compare_vector($vector1, $vector2);
}

# Compare 2 Vectors
sub _compare_vector {
    my ($self, $vector1, $vector2) = @_;
    my $cs = Data::CosineSimilarity->new;
    $cs->add( label1 => $vector1 );
    $cs->add( label2 => $vector2 );
    return $cs->similarity('label1', 'label2')->cosine;
}

1;

__END__

=encoding utf8

=head1 NAME

AI::Embedding - Perl module for working with text embeddings using various APIs